| Age | Commit message (Collapse) | Author |
|---|
|
smatch complain:
drivers/gpu/drm/i915/intel_dsi_pll.c:101 dsi_calc_mnp() error: buffer
overflow 'lfsr_converts' 39 <= 4294967234
and looks justified in doing so.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/1467470166-31717-7-git-send-email-chris@chris-wilson.co.uk
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
|
|
smatch complains:
drivers/gpu/drm/i915/intel_dsi_panel_vbt.c:657 vbt_panel_init() warn:
inconsistent indenting
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/1467470166-31717-6-git-send-email-chris@chris-wilson.co.uk
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
|
|
smatch complains of:
drivers/gpu/drm/i915/intel_fbdev.c:403
intel_fb_initial_config() warn: should '1 << i' be a 64 bit type?
drivers/gpu/drm/i915/intel_fbdev.c:422 intel_fb_initial_config() warn:
should '1 << i' be a 64 bit type?
drivers/gpu/drm/i915/intel_fbdev.c:501 intel_fb_initial_config() warn:
should '1 << i' be a 64 bit type?
We are prepared to iterate over a u64 but don't limit the number of
connectors we try to configure to a maximum of 64.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/1467470166-31717-5-git-send-email-chris@chris-wilson.co.uk
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
|
|
smatch complains:
drivers/gpu/drm/i915/i915_gpu_error.c:503 i915_error_state_to_str()
warn: inconsistent indenting
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/1467470166-31717-4-git-send-email-chris@chris-wilson.co.uk
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
|
|
smatch complains:
drivers/gpu/drm/i915/i915_debugfs.c:1390 i915_frequency_info() Function
too hairy. Giving up.
drivers/gpu/drm/i915/i915_debugfs.c:1985 i915_gem_framebuffer_info()
warn: inconsistent indenting
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/1467470166-31717-3-git-send-email-chris@chris-wilson.co.uk
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
|
|
smatch complains:
drivers/gpu/drm/i915/intel_pm.c:4745 gen6_set_rps_thresholds() warn:
inconsistent indenting
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/1467470166-31717-2-git-send-email-chris@chris-wilson.co.uk
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
|
|
smatch complains:
drivers/gpu/drm/i915/i915_drv.c:1616 i915_drm_resume() warn:
inconsistent indenting
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/1467470166-31717-1-git-send-email-chris@chris-wilson.co.uk
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
|
|
git://people.freedesktop.org/~airlied/linux
Pull drm fixes frlm Dave Airlie:
"Just some AMD and Intel fixes, the AMD ones are further production
Polaris fixes, and the Intel ones fix some early timeouts, some PCI ID
changes and a couple of other fixes.
Still a bit Internet challenged here, hopefully end of next week will
solve it"
* tag 'drm-fixes-for-v4.7-rc6' of git://people.freedesktop.org/~airlied/linux:
drm/i915: Fix missing unlock on error in i915_ppgtt_info()
drm/amd/powerplay: workaround for UVD clock issue
drm/amdgpu: add ACLK_CNTL setting for polaris10
drm/amd/powerplay: fix issue uvd dpm can't enabled on Polaris11.
drm/amd/powerplay: Workaround for Memory EDC Error on Polaris10.
drm/i915: Removing PCI IDs that are no longer listed as Kabylake.
drm/i915: Add more Kabylake PCI IDs.
drm/i915: Avoid early timeout during AUX transfers
drm/i915/hsw: Avoid early timeout during LCPLL disable/restore
drm/i915/lpt: Avoid early timeout during FDI PHY reset
drm/i915/bxt: Avoid early timeout during PLL enable
drm/i915: Refresh cached DP port register value on resume
drm/amd/powerplay: Update CKS on/ CKS off voltage offset calculation
drm/amd/powerplay: disable FFC.
drm/amd/powerplay: add some definition for FFC feature on polaris.
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/broonie/spi
Pull spi fixes from Mark Brown:
"A few small driver-specific fixes for SPI, all in the normal important
if you hit them category especially the rockchip driver fix which
addresses a race which has been exposed more frequently with some
recent performance improvements"
* tag 'spi-fix-v4.7-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/spi:
spi: sunxi: fix transfer timeout
spi: sun4i: fix FIFO limit
spi: rockchip: Signal unfinished DMA transfers
spi: spi-ti-qspi: Suspend the queue before removing the device
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/broonie/regulator
Pull regulator fixes from Mark Brown:
"Two small fixes for the regulator subsystem - one fixing a crash with
one of the devices supported by the max77620 driver, another fixing
startup for the anatop regulator when it starts up with the regulator
in bypass mode"
* tag 'regulator-fix-v4.7-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/regulator:
regulator: max77620: check for valid regulator info
regulator: anatop: allow regulator to be in bypass mode
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/clk/linux
Pull clk fixes from Stephen Boyd:
"A small fix for the newly added oxnas clk driver and a handful of
rockchip clk driver fixes for newly added rk3399 support"
* tag 'clk-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/clk/linux:
clk: Fix return value check in oxnas_stdclk_probe()
clk: rockchip: release io resource when failing to init clk on rk3399
clk: rockchip: fix cpuclk registration error handling
clk: rockchip: Revert "clk: rockchip: reset init state before mmc card initialization"
clk: rockchip: fix incorrect parent for rk3399's {c,g}pll_aclk_perihp_src
clk: rockchip: mark rk3399 GIC clocks as critical
clk: rockchip: initialize flags of clk_init_data in mmc-phase clock
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound into for-linus
ASoC: Fixes for v4.7
A small clutch of hardware specific fixes for various ASoC devices, all
small individually and important if you have that device but not
otherwise.
|
|
drm-next
The patchset contains a new helper in drm_fb_cma_helper.c for suspend/
resume when using cma backed framebuffers.
* 'for-next' of http://git.agner.ch/git/linux-drm-fsl-dcu:
drm/fsl-dcu: disable vblank events on CRTC disable
drm/fsl-dcu: implement suspend/resume using atomic helpers
drm/fsl-dcu: use clk helpers
drm/fsl-dcu: move layer initialization to plane file
drm/fsl-dcu: store layer registers in soc_data
drm/fb_cma_helper: add suspend helper
|
|
Linux 4.7-rc5
The fsl-dcu pull needs -rc3 so go to -rc5 for now.
|
|
http://git.linaro.org/people/benjamin.gaignard/kernel into drm-next
This pull request include 3 minors fix and one feature evolution
around ASoC hdmi codec support.
* 'sti-drm-next-2016-06-30' of http://git.linaro.org/people/benjamin.gaignard/kernel:
drm: sti: Add ASoC generic hdmi codec support.
drm/sti: adjust delay for AWG
drm: sti: fix clocking issues in crtc
drm/sti: Use 64-bit timestamps
|
|
git://anongit.freedesktop.org/drm-intel into drm-fixes
here's a batch of i915 fixes for 4.7.
* tag 'drm-intel-fixes-2016-06-30' of git://anongit.freedesktop.org/drm-intel:
drm/i915: Fix missing unlock on error in i915_ppgtt_info()
drm/i915: Removing PCI IDs that are no longer listed as Kabylake.
drm/i915: Add more Kabylake PCI IDs.
drm/i915: Avoid early timeout during AUX transfers
drm/i915/hsw: Avoid early timeout during LCPLL disable/restore
drm/i915/lpt: Avoid early timeout during FDI PHY reset
drm/i915/bxt: Avoid early timeout during PLL enable
drm/i915: Refresh cached DP port register value on resume
|
|
into drm-fixes
Just a few more late fixes for Polaris cards.
* 'drm-fixes-4.7' of git://people.freedesktop.org/~agd5f/linux:
drm/amd/powerplay: workaround for UVD clock issue
drm/amdgpu: add ACLK_CNTL setting for polaris10
drm/amd/powerplay: fix issue uvd dpm can't enabled on Polaris11.
drm/amd/powerplay: Workaround for Memory EDC Error on Polaris10.
drm/amd/powerplay: Update CKS on/ CKS off voltage offset calculation
drm/amd/powerplay: disable FFC.
drm/amd/powerplay: add some definition for FFC feature on polaris.
|
|
The following testcase may result in a page table entries with a invalid
CCA field being generated:
static void *bindstack;
static int sysrqfd;
static void protect_low(int protect)
{
mprotect(bindstack, BINDSTACK_SIZE, protect);
}
static void sigbus_handler(int signal, siginfo_t * info, void *context)
{
void *addr = info->si_addr;
write(sysrqfd, "x", 1);
printf("sigbus, fault address %p (should not happen, but might)\n",
addr);
abort();
}
static void run_bind_test(void)
{
unsigned int *p = bindstack;
p[0] = 0xf001f001;
write(sysrqfd, "x", 1);
/* Set trap on access to p[0] */
protect_low(PROT_NONE);
write(sysrqfd, "x", 1);
/* Clear trap on access to p[0] */
protect_low(PROT_READ | PROT_WRITE | PROT_EXEC);
write(sysrqfd, "x", 1);
/* Check the contents of p[0] */
if (p[0] != 0xf001f001) {
write(sysrqfd, "x", 1);
/* Reached, but shouldn't be */
printf("badness, shouldn't happen but does\n");
abort();
}
}
int main(void)
{
struct sigaction sa;
sysrqfd = open("/proc/sysrq-trigger", O_WRONLY);
if (sigprocmask(SIG_BLOCK, NULL, &sa.sa_mask)) {
perror("sigprocmask");
return 0;
}
sa.sa_sigaction = sigbus_handler;
sa.sa_flags = SA_SIGINFO | SA_NODEFER | SA_RESTART;
if (sigaction(SIGBUS, &sa, NULL)) {
perror("sigaction");
return 0;
}
bindstack = mmap(NULL,
BINDSTACK_SIZE,
PROT_READ | PROT_WRITE | PROT_EXEC,
MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
if (bindstack == MAP_FAILED) {
perror("mmap bindstack");
return 0;
}
printf("bindstack: %p\n", bindstack);
run_bind_test();
printf("done\n");
return 0;
}
There are multiple ingredients for this:
1) PAGE_NONE is defined to _CACHE_CACHABLE_NONCOHERENT, which is CCA 3
on all platforms except SB1 where it's CCA 5.
2) _page_cachable_default must have bits set which are not set
_CACHE_CACHABLE_NONCOHERENT.
3) Either the defective version of pte_modify for XPA or the standard
version must be in used. However pte_modify for the 36 bit address
space support is no affected.
In that case additional bits in the final CCA mode may generate an invalid
value for the CCA field. On the R10000 system where this was tracked
down for example a CCA 7 has been observed, which is Uncached Accelerated.
Fixed by:
1) Using the proper CCA mode for PAGE_NONE just like for all the other
PAGE_* pte/pmd bits.
2) Fix the two affected variants of pte_modify.
Further code inspection also shows the same issue to exist in pmd_modify
which would affect huge page systems.
Issue in pte_modify tracked down by Alastair Bridgewater, PAGE_NONE
and pmd_modify issue found by me.
The history of this goes back beyond Linus' git history. Chris Dearman's
commit 351336929ccf222ae38ff0cb7a8dd5fd5c6236a0 ("[MIPS] Allow setting of
the cache attribute at run time.") missed the opportunity to fix this
but it was originally introduced in lmo commit
d523832cf12007b3242e50bb77d0c9e63e0b6518 ("Missing from last commit.")
and 32cc38229ac7538f2346918a09e75413e8861f87 ("New configuration option
CONFIG_MIPS_UNCACHED.")
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
Reported-by: Alastair Bridgewater <alastair.bridgewater@gmail.com>
|
|
Since commit 103544d86976 (ACPI,PCI,IRQ: reduce resource requirements)
the penalty values are calculated on the fly rather than at boot time.
This works fine for PCI interrupts but not so well for ISA interrupts.
The information on whether or not an ISA interrupt is in use is not
available to the pci_link.c code directly. That information is
obtained from the outside via acpi_penalize_isa_irq(). [If its
"active" argument is true, then the IRQ is in use by ISA.]
Since the current code relies on PCI Link objects for determination
of penalties, we are factoring in the PCI penalty twice after
acpi_penalize_isa_irq() function is called.
To avoid that, limit the newly added functionality to just PCI
interrupts so that old behavior is still maintained.
Fixes: 103544d86976 (ACPI,PCI,IRQ: reduce resource requirements)
Signed-off-by: Sinan Kaya <okaya@codeaurora.org>
Tested-by: Wim Osterholt <wim@djo.tudelft.nl>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
|
|
Trying to make the ISA and PCI init functionality common turned out
to be a bad idea, because the ISA path depends on external
functionality.
Restore the previous behavior and limit the refactoring to PCI
interrupts only.
Fixes: 1fcb6a813c4f "ACPI,PCI,IRQ: remove redundant code in acpi_irq_penalty_init()"
Signed-off-by: Sinan Kaya <okaya@codeaurora.org>
Tested-by: Wim Osterholt <wim@djo.tudelft.nl>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
|
|
The change introduced in commit 103544d86976 (ACPI,PCI,IRQ: reduce
resource requirements) omitted the initially applied PCI_POSSIBLE
penalty when the IRQ is active.
Incorrect calculation of the penalty leads the ACPI code to assigning
a wrong interrupt number to a PCI INTx interrupt.
This would not be as bad as it sounds in theory. It would just cause
the interrupts to be shared and result in performance penalty.
However, some drivers (like the parallel port driver) don't like
interrupt sharing and in the above case they will causes all of
the PCI drivers wanting to share the interrupt to be unable to
request it.
The issue has not been caught in testing because the behavior is
platform-specific and depends on the peripherals ending up sharing
the IRQ and their drivers.
Before the above commit the code would add the PCI_POSSIBLE value
divided by the number of possible IRQ users to the IRQ penalty
during initialization.
Later in that code path, if the IRQ is chosen as the active IRQ or
if it is used by ISA; additional penalties are added.
Fixes: 103544d86976 (ACPI,PCI,IRQ: reduce resource requirements)
Signed-off-by: Sinan Kaya <okaya@codeaurora.org>
Tested-by: Wim Osterholt <wim@djo.tudelft.nl>
[ rjw: Changelog ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm
Pull ACPI fix from Rafael Wysocki:
"Fix an expression in the ACPI PCI IRQ management code added by a
recent commit that overlooked missing parens in it, so the result of
the computation is incorrect in some cases (Sinan Kaya)"
* tag 'acpi-4.7-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
ACPI,PCI,IRQ: correct operator precedence
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm
Pull power management fixes from Rafael Wysocki:
"Three cpufreq fixes, one in the core (stable-candidate) and two in
drivers (intel_pstate and cpufreq-dt).
Specifics:
- Fix a recent intel_pstate regression that caused the number of
wakeups to increase significantly on an idle system in some cases
due to excessive synchronize_sched() invocations (Rafael Wysocki).
- Fix unnecessary invocations of WARN_ON() in the cpufreq core after
cpufreq has been suspended introduced during the 4.6 cycla (Rafael
Wysocki).
- Fix an error code path in the cpufreq-dt-platdev driver that
forgets to drop a reference to a DT node (Masahiro Yamada)"
* tag 'pm-4.7-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
cpufreq: Avoid false-positive WARN_ON()s in cpufreq_update_policy()
cpufreq: dt: call of_node_put() before error out
intel_pstate: Do not clear utilization update hooks on policy changes
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs
Pull vfs fixes from Al Viro:
"Tmpfs readdir throughput regression fix (this cycle) + some -stable
fodder all over the place.
One missing bit is Miklos' tonight locks.c fix - NFS folks had already
grabbed that one by the time I woke up ;-)"
[ The locks.c fix came through the nfsd tree just moments ago ]
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
namespace: update event counter when umounting a deleted dentry
9p: use file_dentry()
ceph: fix d_obtain_alias() misuses
lockless next_positive()
libfs.c: new helper - next_positive()
dcache_{readdir,dir_lseek}(): don't bother with nested ->d_lock
|
|
Pull lockd/locks fixes from Bruce Fields:
"One fix for lockd soft lookups in an error path, and one fix for file
leases on overlayfs"
* tag 'nfsd-4.7-3' of git://linux-nfs.org/~bfields/linux:
locks: use file_inode()
lockd: unregister notifier blocks if the service fails to come up completely
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/lee/mfd
Pull more MFD fixes from Lee Jones:
"Apologies for missing these from the first pull request.
Final patches fixing Reset API change"
* tag 'mfd-fixes-4.7.1' of git://git.kernel.org/pub/scm/linux/kernel/git/lee/mfd:
usb: dwc3: st: Use explicit reset_control_get_exclusive() API
phy: phy-stih407-usb: Use explicit reset_control_get_exclusive() API
phy: miphy28lp: Inform the reset framework that our reset line may be shared
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm
Pull libnvdimm fixes from Dan Williams:
"1/ Two regression fixes since v4.6: one for the byte order of a sysfs
attribute (bz121161) and another for QEMU 2.6's NVDIMM _DSM (ACPI
Device Specific Method) implementation that gets tripped up by new
auto-probing behavior in the NFIT driver.
2/ A fix tagged for -stable that stops the kernel from
clobbering/ignoring changes to the configuration of a 'pfn'
instance ("struct page" driver). For example changing the
alignment from 2M to 1G may silently revert to 2M if that value is
currently stored on media.
3/ A fix from Eric for an xfstests failure in dax. It is not
currently tagged for -stable since it requires an 8-exabyte file
system to trigger, and there appear to be no user visible side
effects"
* 'libnvdimm-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm:
nfit: fix format interface code byte order
dax: fix offset overflow in dax_io
acpi, nfit: fix acpi_check_dsm() vs zero functions implemented
libnvdimm, pfn, dax: fix initialization vs autodetect for mode + alignment
|
|
Fix incorrect use of nla_strlcpy() where the first NLA_HDRLEN bytes
of the link name where left out.
Making the output of tipc-config -ls look something like:
Link statistics:
dcast-link
1:data0-1.1.2:data0
1:data0-1.1.3:data0
Also, for the record, the patch that introduce this regression
claims "Sending the whole object out can cause a leak". Which isn't
very likely as this is a compat layer, where the data we are parsing
is generated by us and we know the string to be NULL terminated. But
you can of course never be to secure.
Fixes: 5d2be1422e02 (tipc: fix an infoleak in tipc_nl_compat_link_dump)
Signed-off-by: Richard Alpe <richard.alpe@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
On 64bits kernels, device stats are 64bits wide, not 32bits.
Fixes: 80105befdb4b ("net: systemport: add Broadcom SYSTEMPORT Ethernet MAC driver")
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Avoid recursions of dev_queue_xmit() to the wrong net device when
frames are unprotected, since at that time skb->dev still points to
our own macsec dev and unlike macsec_encrypt_finish() dev pointer
doesn't get updated to real underlying device.
Fixes: c09440f7dcb3 ("macsec: introduce IEEE 802.1AE driver")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Sabrina Dubroca <sd@queasysnail.net>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Similar to commit 9b368814b336 ("net: fix bridge multicast packet checksum validation")
we need to fixup the checksum for CHECKSUM_COMPLETE when
pushing skb on RX path. Otherwise we get similar splats.
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Tom Herbert <tom@herbertland.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
People who use PACKET_FANOUT_HASH want a symmetric hash, meaning that
they want packets going in both directions on a flow to hash to the
same bucket.
The core kernel SKB hash became non-symmetric when the ipv6 flow label
and other entities were incorporated into the standard flow hash order
to increase entropy.
But there are no users of PACKET_FANOUT_HASH who want an assymetric
hash, they all want a symmetric one.
Therefore, use the flow dissector to compute a flat symmetric hash
over only the protocol, addresses and ports. This hash does not get
installed into and override the normal skb hash, so this change has
no effect whatsoever on the rest of the stack.
Reported-by: Eric Leblond <eric@regit.org>
Tested-by: Eric Leblond <eric@regit.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Since the tests can and do explicitly check debugfs/i915_ring_missed_irqs
for the handling of a "missed interrupt", adding it to the dmesg at INFO
is just noise. When it happens for real, we still class it as an ERROR.
Note that I have chose to remove it entirely because when we detect the
"missed interrupt" is irrelevant and the message contains no more
information than we glean from looking in debugfs.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1467390209-3576-20-git-send-email-chris@chris-wilson.co.uk
|
|
Borrow the idea from intel_lrc.c to precompute the mask of interrupts we
wish to always enable to avoid having lots of conditionals inside the
interrupt enabling.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1467390209-3576-19-git-send-email-chris@chris-wilson.co.uk
|
|
With only a single callsite for intel_engine_cs->irq_get and ->irq_put,
we can reduce the code size by moving the common preamble into the
caller, and we can also eliminate the reference counting.
For completeness, as we are no longer doing reference counting on irq,
rename the get/put vfunctions to enable/disable respectively and are
able to review the use of posting reads. We only require the
serialisation with hardware when enabling the interrupt (i.e. so we
cannot miss an interrupt by going to sleep before the hardware truly
enables it).
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/1467390209-3576-18-git-send-email-chris@chris-wilson.co.uk
|
|
Under the assumption that enabling signaling will be a frequent
operation, lets preallocate our attachments for signaling inside the
(rather large) request struct (and so benefiting from the slab cache).
v2: Convert from void * to more meaningful names and types.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1467390209-3576-17-git-send-email-chris@chris-wilson.co.uk
|
|
If we convert the tracing over from direct use of ring->irq_get() and
over to the breadcrumb infrastructure, we only have a single user of the
ring->irq_get and so we will be able to simplify the driver routines
(eliminating the redundant validation and irq refcounting).
Process context is preferred over softirq (or even hardirq) for a couple
of reasons:
- we already utilize process context to have fast wakeup of a single
client (i.e. the client waiting for the GPU inspects the seqno for
itself following an interrupt to avoid the overhead of a context
switch before it returns to userspace)
- engine->irq_seqno() is not suitable for use from an softirq/hardirq
context as we may require long waits (100-250us) to ensure the seqno
write is posted before we read it from the CPU
A signaling framework is a requirement for enabling dma-fences.
v2: Move to a signaling framework based upon the waiter.
v3: Track the first-signal to avoid having to walk the rbtree everytime.
v4: Mark the signaler thread as RT priority to reduce latency in the
indirect wakeups.
v5: Make failure to allocate the thread fatal.
v6: Rename kthreads to i915/signal:%u
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1467390209-3576-16-git-send-email-chris@chris-wilson.co.uk
|
|
We have testcases to ensure that seqno wraparound works fine, so we can
forgo forcing everyone to encounter seqno wraparound during early
uptime. seqno wraparound incurs a full GPU stall so not forcing it
will eliminate one jitter from the early system. Using the testcases, we
have very deterministic testing which given how difficult it would be to
debug an issue (GPU hang) stemming from a wraparound using pure
postmortem analysis I see no value in forcing a wrap during boot.
Advancing the global next_seqno after a GPU reset is equally pointless.
References? https://bugs.freedesktop.org/show_bug.cgi?id=95023
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/1467390209-3576-15-git-send-email-chris@chris-wilson.co.uk
|
|
If we flag the seqno as potentially stale upon receiving an interrupt,
we can use that information to reduce the frequency that we apply the
heavyweight coherent seqno read (i.e. if we wake up a chain of waiters).
v2: Use cmpxchg to replace READ_ONCE/WRITE_ONCE for more explicit
control of the ordering wrt to interrupt generation and interrupt
checking in the bottom-half.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1467390209-3576-14-git-send-email-chris@chris-wilson.co.uk
|
|
If we have multiple waiters, we may find that many complete on the same
wake up. If we first inspect the seqno from the CPU cache, we may reduce
the number of heavyweight coherent seqno reads we require.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1467390209-3576-13-git-send-email-chris@chris-wilson.co.uk
|
|
On Ironlake, there is no command nor register to ensure that the write
from a MI_STORE command is completed (and coherent on the CPU) before the
command parser continues. This means that the ordering between the seqno
write and the subsequent user interrupt is undefined (like gen6+). So to
ensure that the seqno write is completed after the final user interrupt
we need to delay the read sufficiently to allow the write to complete.
This delay is undefined by the bspec, and empirically requires 75us even
though a register read combined with a clflush is less than 500ns. Hence,
the delay is due to an on-chip buffer rather than the latency of the write
to memory.
Note that the render ring controls this by filling the PIPE_CONTROL fifo
with stalling commands that force the earliest pipe-control with the
seqno to be completed before the command parser continues. Given that we
need a barrier operation for BSD, we may as well forgo the extra
per-batch latency by using a common per-interrupt barrier.
Studying the impact of adding the usleep shows that in both sequences of
and individual synchronous no-op batches is negligible for the media
engine (where the write now is unordered with the interrupt). Converting
the render engine over from the current glutton of pie-controls over to
the per-interrupt delays speeds up both the sequential and individual
synchronous no-ops by 20% and 60%, respectively. This speed up holds
even when looking at the throughput of small copies (4KiB->4MiB), both
serial and synchronous, by about 20%. This is because despite adding a
significant delay to the interrupt, in all likelihood we will see the
seqno write without having to apply the barrier (only in the rare corner
cases where the write is delayed on the last required is the delay
necessary).
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94307
Testcase: igt/gem_sync #ilk
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1467390209-3576-12-git-send-email-chris@chris-wilson.co.uk
|
|
The gen2 w/a buffer is stuffed into the same slot as the gen5+ scratch
buffer. If we pass in the size we want to allocate for the scratch
buffer, both callers can use the same routine.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1467390209-3576-11-git-send-email-chris@chris-wilson.co.uk
|
|
With the last direct CPU access to the scratch page removed, we can now
allocate it from our small amount of reserved system pages (stolen
memory).
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1467390209-3576-10-git-send-email-chris@chris-wilson.co.uk
|
|
After the elimination of using the scratch page for Ironlake's
breadcrumb, we no longer need to kmap the object. We therefore can move
it into the high unmappable space and do not need to force the object to
be coherent (i.e. snooped on !llc platforms).
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1467390209-3576-9-git-send-email-chris@chris-wilson.co.uk
|
|
By using the same address for storing the HWS on every platform, we can
remove the platform specific vfuncs and reduce the get-seqno routine to
a single read of a cached memory location.
v2: Fix semaphore_passed() to look at the signaling engine (not the
waiter's)
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1467390209-3576-8-git-send-email-chris@chris-wilson.co.uk
|
|
When waiting for an interrupt (waiting for the engine to complete some
work), we know we are the only waiter to be woken on this engine. We also
know when the GPU has nearly completed our request (or at least started
processing it), so after being woken and we detect that the GPU is
active and working on our request, allow us the bottom-half (the first
waiter who wakes up to handle checking the seqno after the interrupt) to
spin for a very short while to reduce client latencies.
The impact is minimal, there was an improvement to the realtime-vs-many
clients case, but exporting the function proves useful later. However,
it is tempting to adjust irq_seqno_barrier to include the spin. The
problem is first ensuring that the "start-of-request" seqno is coherent
as we use that as our basis for judging when it is ok to spin. If we
could, spinning there could dramatically shorten some sleeps, and allow
us to make the barriers more conservative to handle missed seqno writes
on more platforms (all gen7+ are known to have the occasional issue, at
least).
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1467390209-3576-7-git-send-email-chris@chris-wilson.co.uk
|
|
One particularly stressful scenario consists of many independent tasks
all competing for GPU time and waiting upon the results (e.g. realtime
transcoding of many, many streams). One bottleneck in particular is that
each client waits on its own results, but every client is woken up after
every batchbuffer - hence the thunder of hooves as then every client must
do its heavyweight dance to read a coherent seqno to see if it is the
lucky one.
Ideally, we only want one client to wake up after the interrupt and
check its request for completion. Since the requests must retire in
order, we can select the first client on the oldest request to be woken.
Once that client has completed his wait, we can then wake up the
next client and so on. However, all clients then incur latency as every
process in the chain may be delayed for scheduling - this may also then
cause some priority inversion. To reduce the latency, when a client
is added or removed from the list, we scan the tree for completed
seqno and wake up all the completed waiters in parallel.
Using igt/benchmarks/gem_latency, we can demonstrate this effect. The
benchmark measures the number of GPU cycles between completion of a
batch and the client waking up from a call to wait-ioctl. With many
concurrent waiters, with each on a different request, we observe that
the wakeup latency before the patch scales nearly linearly with the
number of waiters (before external factors kick in making the scaling much
worse). After applying the patch, we can see that only the single waiter
for the request is being woken up, providing a constant wakeup latency
for every operation. However, the situation is not quite as rosy for
many waiters on the same request, though to the best of my knowledge this
is much less likely in practice. Here, we can observe that the
concurrent waiters incur extra latency from being woken up by the
solitary bottom-half, rather than directly by the interrupt. This
appears to be scheduler induced (having discounted adverse effects from
having a rbtree walk/erase in the wakeup path), each additional
wake_up_process() costs approximately 1us on big core. Another effect of
performing the secondary wakeups from the first bottom-half is the
incurred delay this imposes on high priority threads - rather than
immediately returning to userspace and leaving the interrupt handler to
wake the others.
To offset the delay incurred with additional waiters on a request, we
could use a hybrid scheme that did a quick read in the interrupt handler
and dequeued all the completed waiters (incurring the overhead in the
interrupt handler, not the best plan either as we then incur GPU
submission latency) but we would still have to wake up the bottom-half
every time to do the heavyweight slow read. Or we could only kick the
waiters on the seqno with the same priority as the current task (i.e. in
the realtime waiter scenario, only it is woken up immediately by the
interrupt and simply queues the next waiter before returning to userspace,
minimising its delay at the expense of the chain, and also reducing
contention on its scheduler runqueue). This is effective at avoid long
pauses in the interrupt handler and at avoiding the extra latency in
realtime/high-priority waiters.
v2: Convert from a kworker per engine into a dedicated kthread for the
bottom-half.
v3: Rename request members and tweak comments.
v4: Use a per-engine spinlock in the breadcrumbs bottom-half.
v5: Fix race in locklessly checking waiter status and kicking the task on
adding a new waiter.
v6: Fix deciding when to force the timer to hide missing interrupts.
v7: Move the bottom-half from the kthread to the first client process.
v8: Reword a few comments
v9: Break the busy loop when the interrupt is unmasked or has fired.
v10: Comments, unnecessary churn, better debugging from Tvrtko
v11: Wake all completed waiters on removing the current bottom-half to
reduce the latency of waking up a herd of clients all waiting on the
same request.
v12: Rearrange missed-interrupt fault injection so that it works with
igt/drv_missed_irq_hang
v13: Rename intel_breadcrumb and friends to intel_wait in preparation
for signal handling.
v14: RCU commentary, assert_spin_locked
v15: Hide BUG_ON behind the compiler; report on gem_latency findings.
v16: Sort seqno-groups by priority so that first-waiter has the highest
task priority (and so avoid priority inversion).
v17: Add waiters to post-mortem GPU hang state.
v18: Return early for a completed wait after acquiring the spinlock.
Avoids adding ourselves to the tree if the is already complete, and
skips the awkward question of why we don't do completion wakeups for
waits earlier than or equal to ourselves.
v19: Prepare for init_breadcrumbs to fail. Later patches may want to
allocate during init, so be prepared to propagate back the error code.
Testcase: igt/gem_concurrent_blit
Testcase: igt/benchmarks/gem_latency
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: "Rogozhkin, Dmitry V" <dmitry.v.rogozhkin@intel.com>
Cc: "Gong, Zhipeng" <zhipeng.gong@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: Dave Gordon <david.s.gordon@intel.com>
Cc: "Goel, Akash" <akash.goel@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com> #v18
Link: http://patchwork.freedesktop.org/patch/msgid/1467390209-3576-6-git-send-email-chris@chris-wilson.co.uk
|
|
Currently __i915_wait_request uses a per-engine wait_queue_t for the dual
purpose of waking after the GPU advances or for waking after an error.
In the future, we may add even more wake sources and require greater
separation, but for now we can conceptually simplify wakeups by separating
the two sources. In particular, this allows us to use different wait-queues
(e.g. one on the engine advancement, a global one for errors and one on
each requests) without any hassle.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1467390209-3576-5-git-send-email-chris@chris-wilson.co.uk
|
|
Since the function is a small wrapper around schedule_delayed_work(),
move it inline to remove the function call overhead for the principle
caller.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1467390209-3576-4-git-send-email-chris@chris-wilson.co.uk
|
|
The queue only ever contains at most one item and has no special flags.
It is just a very simple wrapper around the system-wq - a complication
with no benefits.
v2: Use the system_long_wq as we may wish to capture the error state
after detecting the hang - which may take a bit of time.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1467390209-3576-3-git-send-email-chris@chris-wilson.co.uk
|
